INDEX

Explanations

references to methods or processes used in scientific experiments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"as" followed by a reference

np_acts-logits-general · gemini-2.0-flash

as a reference or basis

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <>",

-0.70

HideFlags

-0.70

richTextPanel

-0.68

 itſelf

-0.67

 defaultstate

-0.66

 >=",

-0.63

ConstraintMaker

-0.61

MLLoader

-0.60

 MERCHANTABILITY

-0.60

 useAppContext

-0.59

POSITIVE LOGITS

 reference

1.15

reference

0.94

 REFERENCE

0.86

 Reference

0.86

 basis

0.84

 inspiration

0.81

 referencia

0.81

Reference

0.79

 guide

0.79

 refer

0.79

Activations Density 0.609%

references to methods or processes used in scientific experiments

"as" followed by a reference

as a reference or basis

No Comments

No Known Activations